论文部分内容阅读
针对铜冶炼过程中的能耗难以预测的问题,提出基于支持向量回归的铜冶炼节能过程参数优化学习方法:,首先分析影响铜能耗的各种参数,然后利支持向量回归算法对输入参数和输出能耗之间的关系进行训练,从而筛选出最优参数,为生产能耗控制模型提供了基础。实验结果:表明,提出方法:较传统的BP神经网络算法相比具有学习速度快,收敛性好,泛化能力强等特点,且能耗预测的平均相对误差小于7%。
Aiming at the problem of unpredictable energy consumption in copper smelting process, a method based on support vector regression is proposed to optimize the parameters of copper smelting energy saving process. Firstly, the various parameters that affect copper energy consumption are analyzed. Then the support vector regression Output the relationship between energy consumption for training, which filter out the optimal parameters for the production of energy control model provides the foundation. The experimental results show that the proposed method has the characteristics of fast learning speed, good convergence and generalization ability compared with the traditional BP neural network algorithm. The average relative error of energy consumption prediction is less than 7%.